spark MinHashLSHExample 源码

spark MinHashLSHExample 代码

文件路径：/examples/src/main/scala/org/apache/spark/examples/ml/MinHashLSHExample.scala

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

// scalastyle:off println
package org.apache.spark.examples.ml

// $example on$
import org.apache.spark.ml.feature.MinHashLSH
import org.apache.spark.ml.linalg.Vectors
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.functions.col
// $example off$

/**
 * An example demonstrating MinHashLSH.
 * Run with:
 *   bin/run-example ml.MinHashLSHExample
 */
object MinHashLSHExample {
  def main(args: Array[String]): Unit = {
    // Creates a SparkSession
    val spark = SparkSession
      .builder
      .appName("MinHashLSHExample")
      .getOrCreate()

    // $example on$
    val dfA = spark.createDataFrame(Seq(
      (0, Vectors.sparse(6, Seq((0, 1.0), (1, 1.0), (2, 1.0)))),
      (1, Vectors.sparse(6, Seq((2, 1.0), (3, 1.0), (4, 1.0)))),
      (2, Vectors.sparse(6, Seq((0, 1.0), (2, 1.0), (4, 1.0))))
    )).toDF("id", "features")

    val dfB = spark.createDataFrame(Seq(
      (3, Vectors.sparse(6, Seq((1, 1.0), (3, 1.0), (5, 1.0)))),
      (4, Vectors.sparse(6, Seq((2, 1.0), (3, 1.0), (5, 1.0)))),
      (5, Vectors.sparse(6, Seq((1, 1.0), (2, 1.0), (4, 1.0))))
    )).toDF("id", "features")

    val key = Vectors.sparse(6, Seq((1, 1.0), (3, 1.0)))

    val mh = new MinHashLSH()
      .setNumHashTables(5)
      .setInputCol("features")
      .setOutputCol("hashes")

    val model = mh.fit(dfA)

    // Feature Transformation
    println("The hashed dataset where hashed values are stored in the column 'hashes':")
    model.transform(dfA).show()

    // Compute the locality sensitive hashes for the input rows, then perform approximate
    // similarity join.
    // We could avoid computing hashes by passing in the already-transformed dataset, e.g.
    // `model.approxSimilarityJoin(transformedA, transformedB, 0.6)`
    println("Approximately joining dfA and dfB on Jaccard distance smaller than 0.6:")
    model.approxSimilarityJoin(dfA, dfB, 0.6, "JaccardDistance")
      .select(col("datasetA.id").alias("idA"),
        col("datasetB.id").alias("idB"),
        col("JaccardDistance")).show()

    // Compute the locality sensitive hashes for the input rows, then perform approximate nearest
    // neighbor search.
    // We could avoid computing hashes by passing in the already-transformed dataset, e.g.
    // `model.approxNearestNeighbors(transformedA, key, 2)`
    // It may return less than 2 rows when not enough approximate near-neighbor candidates are
    // found.
    println("Approximately searching dfA for 2 nearest neighbors of the key:")
    model.approxNearestNeighbors(dfA, key, 2).show()
    // $example off$

    spark.stop()
  }
}
// scalastyle:on println

相关信息

spark 源码目录

相关文章

spark AFTSurvivalRegressionExample 源码

spark ALSExample 源码

spark BinarizerExample 源码

spark BisectingKMeansExample 源码

spark BucketedRandomProjectionLSHExample 源码

spark BucketizerExample 源码

spark ChiSqSelectorExample 源码

spark ChiSquareTestExample 源码

spark CorrelationExample 源码

spark CountVectorizerExample 源码